Struct EnergyBasedModel 

pub struct EnergyBasedModel { /* private fields */ }

Energy-based model for semi-supervised learning

This implements an energy-based model that learns to assign low energy to data samples and high energy to unlikely samples. The model combines energy minimization with classification for semi-supervised learning.

Implementations

impl EnergyBasedModel

pub fn new() -> Self

Create a new energy-based model

pub fn hidden_dims(self, dims: Vec<usize>) -> Self

Set the hidden layer dimensions

pub fn n_classes(self, n_classes: usize) -> Self

Set the number of classes

pub fn input_dim(self, input_dim: usize) -> Self

Set the input dimension

pub fn learning_rate(self, lr: f64) -> Self

Set the learning rate

pub fn epochs(self, epochs: usize) -> Self

Set the number of epochs

pub fn regularization(self, reg: f64) -> Self

Set the regularization parameter

pub fn n_negative_samples(self, n_samples: usize) -> Self

Set the number of negative samples

pub fn temperature(self, temp: f64) -> Self

Set the temperature parameter

pub fn classification_weight(self, weight: f64) -> Self

Set the classification weight

pub fn margin(self, margin: f64) -> Self

Set the contrastive margin

pub fn energy_to_probability(&self, energy: f64) -> f64

Compute Boltzmann probability from energy

pub fn langevin_sample( &self, initial_sample: &ArrayView1<'_, f64>, n_steps: usize, step_size: f64, ) -> Result<Array1<f64>, SklearsError>

Sample from the model using Langevin dynamics

pub fn log_partition_function( &self, n_samples: usize, ) -> Result<f64, SklearsError>

Compute the partition function approximation

Trait Implementations

impl Clone for EnergyBasedModel

fn clone(&self) -> EnergyBasedModel

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for EnergyBasedModel

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for EnergyBasedModel

fn default() -> Self

Returns the “default value” for a type.

impl Fit<ArrayBase<ViewRepr<&f64>, Dim<[usize; 2]>>, ArrayBase<ViewRepr<&i32>, Dim<[usize; 1]>>> for EnergyBasedModel

type Fitted = EnergyBasedModel

The fitted model type

fn fit( self, X: &ArrayView2<'_, f64>, y: &ArrayView1<'_, i32>, ) -> Result<Self::Fitted, SklearsError>

Fit the model to the provided data with validation

fn fit_with_validation( self, x: &X, y: &Y, _x_val: Option<&X>, _y_val: Option<&Y>, ) -> Result<(Self::Fitted, FitMetrics), SklearsError>

where Self: Sized,

Fit with custom validation and early stopping

impl Predict<ArrayBase<ViewRepr<&f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<i32>, Dim<[usize; 1]>>> for EnergyBasedModel

fn predict(&self, X: &ArrayView2<'_, f64>) -> Result<Array1<i32>, SklearsError>

Make predictions on the provided data

fn predict_with_uncertainty( &self, x: &X, ) -> Result<(Output, UncertaintyMeasure), SklearsError>

Make predictions with confidence intervals

impl PredictProba<ArrayBase<ViewRepr<&f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>> for EnergyBasedModel

fn predict_proba( &self, X: &ArrayView2<'_, f64>, ) -> Result<Array2<f64>, SklearsError>

Predict class probabilities